Examples with Corpus com.ibm.watson.speech_to_text.v1.model.Corpus used on opensource projects

Example 1 with Corpus

use of com.ibm.watson.speech_to_text.v1.model.Corpus in project java-sdk by watson-developer-cloud.

the class CustomizationExample method main.

/**
 * The main method.
 *
 * @param args the arguments
 * @throws InterruptedException the interrupted exception
 */
public static void main(String[] args) throws InterruptedException {
    SpeechToText service = new SpeechToText();
    service.setUsernameAndPassword("<username>", "<password>");
    // Create language model
    CreateLanguageModelOptions createOptions = new CreateLanguageModelOptions.Builder().name("IEEE-permanent").baseModelName("en-US_BroadbandModel").description("My customization").build();
    LanguageModel myModel = service.createLanguageModel(createOptions).execute();
    String id = myModel.getCustomizationId();
    try {
        // Add a corpus file to the model
        AddCorpusOptions addOptions = new AddCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").corpusFile(new File(CORPUS_FILE)).corpusFileContentType(HttpMediaType.TEXT_PLAIN).allowOverwrite(false).build();
        service.addCorpus(addOptions).execute();
        // Get corpus status
        GetCorpusOptions getOptions = new GetCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").build();
        for (int x = 0; x < 30 && (service.getCorpus(getOptions).execute()).getStatus() != Status.ANALYZED; x++) {
            Thread.sleep(5000);
        }
        // Get all corpora
        ListCorporaOptions listCorporaOptions = new ListCorporaOptions.Builder().customizationId(id).build();
        Corpora corpora = service.listCorpora(listCorporaOptions).execute();
        System.out.println(corpora);
        // Get specific corpus
        Corpus corpus = service.getCorpus(getOptions).execute();
        System.out.println(corpus);
        // Now add some user words to the custom model
        service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("IEEE").word("IEEE").displayAs("IEEE").addSoundsLike("I. triple E.").build()).execute();
        service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("hhonors").word("hhonors").displayAs("IEEE").addSoundsLike("H. honors").addSoundsLike("Hilton honors").build()).execute();
        // Display all words in the words resource (OOVs from the corpus and
        // new words just added) in ascending alphabetical order
        ListWordsOptions listWordsAlphabeticalOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).build();
        Words words = service.listWords(listWordsAlphabeticalOptions).execute();
        System.out.println("\nASCENDING ALPHABETICAL ORDER:");
        System.out.println(words);
        // Then display all words in the words resource in descending order
        // by count
        ListWordsOptions listWordsCountOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).sort("-" + ListWordsOptions.Sort.COUNT).build();
        words = service.listWords(listWordsCountOptions).execute();
        System.out.println("\nDESCENDING ORDER BY COUNT:");
        System.out.println(words);
        // Now start training of the model
        TrainLanguageModelOptions trainOptions = new TrainLanguageModelOptions.Builder().customizationId(id).wordTypeToAdd(TrainLanguageModelOptions.WordTypeToAdd.ALL).build();
        service.trainLanguageModel(trainOptions).execute();
        for (int x = 0; x < 30 && myModel.getStatus() != LanguageModel.Status.AVAILABLE; x++) {
            GetLanguageModelOptions getOptions = new GetLanguageModelOptions.Builder().customizationId(id).build();
            myModel = service.getLanguageModel(getOptions).execute();
            Thread.sleep(10000);
        }
        File audio = new File(AUDIO_FILE);
        RecognizeOptions recognizeOptionsWithModel = new RecognizeOptions.Builder().model(RecognizeOptions.EN_US_BROADBANDMODEL).customizationId(id).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
        RecognizeOptions recognizeOptionsWithoutModel = new RecognizeOptions.Builder().model(RecognizeOptions.EN_US_BROADBANDMODEL).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
        // First decode WITHOUT the custom model
        SpeechRecognitionResults transcript = service.recognize(recognizeOptionsWithoutModel).execute();
        System.out.println(transcript);
        // Now decode with the custom model
        transcript = service.recognize(recognizeOptionsWithModel).execute();
        System.out.println(transcript);
    } finally {
        DeleteLanguageModelOptions deleteOptions = new DeleteLanguageModelOptions.Builder().customizationId(id).build();
        service.deleteLanguageModel(deleteOptions).execute();
    }
}

Example 2 with Corpus

use of com.ibm.watson.speech_to_text.v1.model.Corpus in project java-sdk by watson-developer-cloud.

the class SpeechToText method listCorpora.

/**
 * List corpora.
 *
 * <p>Lists information about all corpora from a custom language model. The information includes
 * the name, status, and total number of words for each corpus. _For custom models that are based
 * on previous-generation models_, it also includes the number of out-of-vocabulary (OOV) words
 * from the corpus. You must use credentials for the instance of the service that owns a model to
 * list its corpora.
 *
 * <p>**See also:** [Listing corpora for a custom language
 * model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-manageCorpora#listCorpora).
 *
 * @param listCorporaOptions the {@link ListCorporaOptions} containing the options for the call
 * @return a {@link ServiceCall} with a result of type {@link Corpora}
 */
public ServiceCall<Corpora> listCorpora(ListCorporaOptions listCorporaOptions) {
    com.ibm.cloud.sdk.core.util.Validator.notNull(listCorporaOptions, "listCorporaOptions cannot be null");
    Map<String, String> pathParamsMap = new HashMap<String, String>();
    pathParamsMap.put("customization_id", listCorporaOptions.customizationId());
    RequestBuilder builder = RequestBuilder.get(RequestBuilder.resolveRequestUrl(getServiceUrl(), "/v1/customizations/{customization_id}/corpora", pathParamsMap));
    Map<String, String> sdkHeaders = SdkCommon.getSdkHeaders("speech_to_text", "v1", "listCorpora");
    for (Entry<String, String> header : sdkHeaders.entrySet()) {
        builder.header(header.getKey(), header.getValue());
    }
    builder.header("Accept", "application/json");
    ResponseConverter<Corpora> responseConverter = ResponseConverterUtils.getValue(new com.google.gson.reflect.TypeToken<Corpora>() {
    }.getType());
    return createServiceCall(builder.build(), responseConverter);
}

Example 3 with Corpus

use of com.ibm.watson.speech_to_text.v1.model.Corpus in project java-sdk by watson-developer-cloud.

the class SpeechToText method trainLanguageModel.

/**
 * Train a custom language model.
 *
 * <p>Initiates the training of a custom language model with new resources such as corpora,
 * grammars, and custom words. After adding, modifying, or deleting resources for a custom
 * language model, use this method to begin the actual training of the model on the latest data.
 * You can specify whether the custom language model is to be trained with all words from its
 * words resource or only with words that were added or modified by the user directly. You must
 * use credentials for the instance of the service that owns a model to train it.
 *
 * <p>The training method is asynchronous. It can take on the order of minutes to complete
 * depending on the amount of data on which the service is being trained and the current load on
 * the service. The method returns an HTTP 200 response code to indicate that the training process
 * has begun.
 *
 * <p>You can monitor the status of the training by using the [Get a custom language
 * model](#getlanguagemodel) method to poll the model's status. Use a loop to check the status
 * every 10 seconds. The method returns a `LanguageModel` object that includes `status` and
 * `progress` fields. A status of `available` means that the custom model is trained and ready to
 * use. The service cannot accept subsequent training requests or requests to add new resources
 * until the existing request completes.
 *
 * <p>**See also:** * [Train the custom language
 * model](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-languageCreate#trainModel-language)
 * * [Language support for
 * customization](https://cloud.ibm.com/docs/speech-to-text?topic=speech-to-text-custom-support)
 *
 * <p>### Training failures
 *
 * <p>Training can fail to start for the following reasons: * The service is currently handling
 * another request for the custom model, such as another training request or a request to add a
 * corpus or grammar to the model. * No training data have been added to the custom model. * The
 * custom model contains one or more invalid corpora, grammars, or words (for example, a custom
 * word has an invalid sounds-like pronunciation). You can correct the invalid resources or set
 * the `strict` parameter to `false` to exclude the invalid resources from the training. The model
 * must contain at least one valid resource for training to succeed.
 *
 * @param trainLanguageModelOptions the {@link TrainLanguageModelOptions} containing the options
 *     for the call
 * @return a {@link ServiceCall} with a result of type {@link TrainingResponse}
 */
public ServiceCall<TrainingResponse> trainLanguageModel(TrainLanguageModelOptions trainLanguageModelOptions) {
    com.ibm.cloud.sdk.core.util.Validator.notNull(trainLanguageModelOptions, "trainLanguageModelOptions cannot be null");
    Map<String, String> pathParamsMap = new HashMap<String, String>();
    pathParamsMap.put("customization_id", trainLanguageModelOptions.customizationId());
    RequestBuilder builder = RequestBuilder.post(RequestBuilder.resolveRequestUrl(getServiceUrl(), "/v1/customizations/{customization_id}/train", pathParamsMap));
    Map<String, String> sdkHeaders = SdkCommon.getSdkHeaders("speech_to_text", "v1", "trainLanguageModel");
    for (Entry<String, String> header : sdkHeaders.entrySet()) {
        builder.header(header.getKey(), header.getValue());
    }
    builder.header("Accept", "application/json");
    if (trainLanguageModelOptions.wordTypeToAdd() != null) {
        builder.query("word_type_to_add", String.valueOf(trainLanguageModelOptions.wordTypeToAdd()));
    }
    if (trainLanguageModelOptions.customizationWeight() != null) {
        builder.query("customization_weight", String.valueOf(trainLanguageModelOptions.customizationWeight()));
    }
    ResponseConverter<TrainingResponse> responseConverter = ResponseConverterUtils.getValue(new com.google.gson.reflect.TypeToken<TrainingResponse>() {
    }.getType());
    return createServiceCall(builder.build(), responseConverter);
}

Example 4 with Corpus

use of com.ibm.watson.speech_to_text.v1.model.Corpus in project java-sdk by watson-developer-cloud.

the class CustomizationExample method main.

/**
 * The main method.
 *
 * @param args the arguments
 * @throws InterruptedException the interrupted exception
 */
public static void main(String[] args) throws InterruptedException, FileNotFoundException {
    Authenticator authenticator = new IamAuthenticator("<iam_api_key>");
    SpeechToText service = new SpeechToText(authenticator);
    // Create language model
    CreateLanguageModelOptions createOptions = new CreateLanguageModelOptions.Builder().name("IEEE-permanent").baseModelName("en-US_BroadbandModel").description("My customization").build();
    LanguageModel myModel = service.createLanguageModel(createOptions).execute().getResult();
    String id = myModel.getCustomizationId();
    try {
        // Add a corpus file to the model
        AddCorpusOptions addOptions = new AddCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").corpusFile(new File(CORPUS_FILE)).allowOverwrite(false).build();
        service.addCorpus(addOptions).execute().getResult();
        // Get corpus status
        GetCorpusOptions getOptions = new GetCorpusOptions.Builder().customizationId(id).corpusName("corpus-1").build();
        for (int x = 0; x < 30 && !service.getCorpus(getOptions).execute().getResult().getStatus().equals(Corpus.Status.ANALYZED); x++) {
            Thread.sleep(5000);
        }
        // Get all corpora
        ListCorporaOptions listCorporaOptions = new ListCorporaOptions.Builder().customizationId(id).build();
        Corpora corpora = service.listCorpora(listCorporaOptions).execute().getResult();
        System.out.println(corpora);
        // Get specific corpus
        Corpus corpus = service.getCorpus(getOptions).execute().getResult();
        System.out.println(corpus);
        // Now add some user words to the custom model
        service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("IEEE").word("IEEE").displayAs("IEEE").addSoundsLike("I. triple E.").build()).execute();
        service.addWord(new AddWordOptions.Builder().customizationId(id).wordName("hhonors").word("hhonors").displayAs("IEEE").addSoundsLike("H. honors").addSoundsLike("Hilton honors").build()).execute();
        // Display all words in the words resource (OOVs from the corpus and
        // new words just added) in ascending alphabetical order
        ListWordsOptions listWordsAlphabeticalOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).build();
        Words words = service.listWords(listWordsAlphabeticalOptions).execute().getResult();
        System.out.println("\nASCENDING ALPHABETICAL ORDER:");
        System.out.println(words);
        // Then display all words in the words resource in descending order
        // by count
        ListWordsOptions listWordsCountOptions = new ListWordsOptions.Builder().customizationId(id).wordType(ListWordsOptions.WordType.ALL).sort("-" + ListWordsOptions.Sort.COUNT).build();
        words = service.listWords(listWordsCountOptions).execute().getResult();
        System.out.println("\nDESCENDING ORDER BY COUNT:");
        System.out.println(words);
        // Now start training of the model
        TrainLanguageModelOptions trainOptions = new TrainLanguageModelOptions.Builder().customizationId(id).wordTypeToAdd(TrainLanguageModelOptions.WordTypeToAdd.ALL).build();
        service.trainLanguageModel(trainOptions).execute();
        for (int x = 0; x < 30 && !myModel.getStatus().equals(LanguageModel.Status.AVAILABLE); x++) {
            GetLanguageModelOptions getLanguageModelOptions = new GetLanguageModelOptions.Builder().customizationId(id).build();
            myModel = service.getLanguageModel(getLanguageModelOptions).execute().getResult();
            Thread.sleep(10000);
        }
        File audio = new File(AUDIO_FILE);
        RecognizeOptions recognizeOptionsWithModel = new RecognizeOptions.Builder().model(RecognizeOptions.Model.EN_US_BROADBANDMODEL).customizationId(id).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
        RecognizeOptions recognizeOptionsWithoutModel = new RecognizeOptions.Builder().model(RecognizeOptions.Model.EN_US_BROADBANDMODEL).audio(audio).contentType(HttpMediaType.AUDIO_WAV).build();
        // First decode WITHOUT the custom model
        SpeechRecognitionResults transcript = service.recognize(recognizeOptionsWithoutModel).execute().getResult();
        System.out.println(transcript);
        // Now decode with the custom model
        transcript = service.recognize(recognizeOptionsWithModel).execute().getResult();
        System.out.println(transcript);
    } finally {
        DeleteLanguageModelOptions deleteOptions = new DeleteLanguageModelOptions.Builder().customizationId(id).build();
        service.deleteLanguageModel(deleteOptions).execute();
    }
}

Example 5 with Corpus

use of com.ibm.watson.speech_to_text.v1.model.Corpus in project java-sdk by watson-developer-cloud.

the class SpeechToTextIT method testGetCorpus.

/**
 * Test get corpus.
 */
@Test
@Ignore
public void testGetCorpus() {
    GetCorpusOptions getOptions = new GetCorpusOptions.Builder().corpusName("foo3").customizationId(customizationId).build();
    Corpus result = service.getCorpus(getOptions).execute().getResult();
    assertNotNull(result);
}